Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024;13(4):42-63.
doi: 10.5539/ijsp.v13n4p42. Epub 2024 Nov 30.

Classification of Pneumonia, Tuberculosis and Covid-19 from Chest X-Ray Images Using Convolution Neural Network Model

J Kiche  1 , Ivivi Mwaniki  2 , Idah Orowe  1 , Patrick Weke  1
Affiliations

Classification of Pneumonia, Tuberculosis and Covid-19 from Chest X-Ray Images Using Convolution Neural Network Model

J Kiche et al. Int J Stat Probab. 2024.

Abstract

Accurate and timely diagnosis of respiratory ailments like pneumonia, tuberculosis (TB), and COVID-19 is pivotal for effective patient care and public health interventions. Deep learning algorithms have emerged as potent tools in medical image classification, offering promise for automated diagnosis and screening. This study presents a deep learning-based approach for categorizing chest X-ray images into three classes: pneumonia, tuberculosis, and COVID-19. Utilizing convolutional neural networks (CNNs) as the primary architecture, owing to their ability to automatically extract relevant features from raw image data. The proposed model is trained on a sizable dataset of chest X-ray images annotated with ground truth labels for pneumonia, TB, and COVID-19. Extensive experiments are conducted to evaluate the model's performance in terms of classification accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). Additionally, we compare the performance of our deep learning model with traditional machine learning techniques, including support vector machines, decision trees, XGBoost, and evaluate its performance on an independent test set. Our findings demonstrate that the proposed deep learning model achieves high accuracy in classifying chest X-ray images of pneumonia, TB, and COVID-19, outperforming traditional methods and showing potential for clinical deployment as a screening tool, especially in resource-limited settings.

Keywords: AUC-ROC-Area Under the Receiver Operating Characteristic Curve; CNN-Convolutional Neural Networks; PMI-Pointwise Mutual Information.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
Global incidence of pneumonia, tuberculosis, and COVID-19 in 2024
Figure 2.
Figure 2.
Incidence of pneumonia, tuberculosis, and COVID-19 in Africa in 2024
Figure 3.
Figure 3.
Incidence of pneumonia, tuberculosis, and COVID-19 in Kenya in 2024
Figure 4.
Figure 4.
Sigmoid Activation Function
Figure 5.
Figure 5.
Tanh Activation Function
Figure 6.
Figure 6.
ReLU Activation Function
Figure 7.
Figure 7.
Softmax Activation Function for a Single Input in a Vector of Multiple Classes
Figure 8.
Figure 8.
SGD Optimization Path on a Simple Quadratic Loss Function
Figure 9.
Figure 9.
Class distribution by set
Figure 10.
Figure 10.
COVID19 image in train set
Figure 11.
Figure 11.
NORMAL image in train set
Figure 12.
Figure 12.
PNEUMONIA image in train set
Figure 13.
Figure 13.
TUBERCULOSIS image in train set
Figure 14.
Figure 14.
COVID19 image in test set
Figure 15.
Figure 15.
NORMAL image in test set
Figure 16.
Figure 16.
PNEUMONIA image in test set
Figure 17.
Figure 17.
TUBERCULOSIS image in test set
Figure 18.
Figure 18.
COVID19 image in val set
Figure 19.
Figure 19.
NORMAL image in val set
Figure 20.
Figure 20.
PNEUMONIA image in val set
Figure 21.
Figure 21.
TUBERCULOSIS image in val set
Figure 22.
Figure 22.
Accuracy Function Evolution
Figure 23.
Figure 23.
Loss function evolution
Figure 24.
Figure 24.
Loss function evolution
Figure 25.
Figure 25.
True Covid19 predicted as Covid19
Figure 26.
Figure 26.
True Normal predicted as Pneumonia
Figure 27.
Figure 27.
True Normal predicted as Tuberculosis
Figure 28.
Figure 28.
True Pneumonia predicted as Pneumonia
Figure 29.
Figure 29.
True Pneumonia predicted as Normal
Figure 30.
Figure 30.
True Tuberculosis predicted as Tuberculosis
See this image and copyright information in PMC

References

    1. Bishop CM (2006). Pattern recognition. In Barber D, Bishop C, & Titterington M (Eds.), Neural networks and machine learning (pp. 3–17).
    1. Brownlee J (2023, January 15). How to use LSTM networks for time series forecasting in Python. Machine Learning Mastery.
    1. Butt C, Gill J, Chun D, Babar M, & Sah I (2019). Deep learning system to screen coronavirus disease 2019 pneumonia. Applied Intelligence, 51(1), 1–7. - PMC - PubMed
    1. Deng J, Dong W, Socher R, Li L-J, Li K, & Fei-Fei L (2009). ImageNet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition (pp. 248–255).
    1. Guan X, Zhong Y, & Liu X (2018). Towards automatic diagnosis of pulmonary diseases based on CT images and deep learning. IEEE Access, 6, 77770–77779.

LinkOut - more resources